Evaluating the Effectiveness and Challenges of the Solid Waste Management System in Lilongwe City Council, Malawi
Posture and Stress Detection System using Open CV and Media Pipe
City Council Help Desk Support System
DDoS Attacks Detection using Different Decision Tree Algorithms
Comprehensive Study on Blockchain Dynamic Learning Methods
Efficient Agent Based Priority Scheduling and LoadBalancing Using Fuzzy Logic in Grid Computing
A Survey of Various Task Scheduling Algorithms In Cloud Computing
Integrated Atlas Based Localisation Features in Lungs Images
A Computational Intelligence Technique for Effective Medical Diagnosis Using Decision Tree Algorithm
A Viable Solution to Prevent SQL Injection Attack Using SQL Injection
The evaluation of lecturers by students in higher institutions is important to monitor and control academic quality. This work was conducted to evaluate lecturers' teaching methods in Federal University of Technology (FUT Minna) using survey evaluation technique and implemented on a JavaFX platform. The scope of this work is for all undergraduate students in FUT Minna and quality assurance staff. The Lecturer Evaluation System (LES) was developed integrating various components in computer science. The participants for the LES were drawn from various departments in the institution consisting of 20 students each from 100 to 500 levels. The LES was evaluated using the System Usability Scale (SUS) and aggregations were obtained from students' reviews. Results showed that 90% of 400 level students and 60% of 200 students level preferred the system, 40% of 100 level students found the system’s usage tedious, 50% of the 300 level students and 30% of 500 level students found the system cumbersome to operate. It was concluded that the system was easy to interact with, workability process was not complex, and it could be used to assess lecturers' teaching methods.
The exponential rate at which textual information is being generated over the internet makes extracting useful knowledge from these vast volumes of information essential and increasingly important. Analysis of sentiments or opinion engineering plays a vital role in retrieving actionable knowledge from users or customer web reviews. Sentiment analysis of movie reviews help users to quickly determine which movie to purchase or watch. Also, it helps movie producers to get customers feedback on their movies. This paper presents a movie reviews sentiment classification model using Naïve Bayes (NB), Support Vector Machine (SVM), and K-Nearest Neighbors (KNN). Prior to building sentiment classification models, data pre-processing techniques were applied on the labelled polarity movie reviews dataset. The most important features (unigram and the mixed-unibigram) were extracted from the dataset using Term Frequency (TF) and Term Inverse Document Frequency (TF-IDF) feature extraction techniques. The extracted features were classified using three (NB, SVM, and KNN) supervised machine learning algorithms. The result of the implementation shows that KNN had 95.9% accuracy with TF and mixed-unibigram features, NB and SVM had an accuracy of 90.6% and 92.22%, respectively. Therefore, the result shows that KNN gives the best performance.
In order to have a web of relevant information retrieval otherwise, known as semantic web, ontology has been identified as its core stronghold to actualize the dream. Ontology is a data modeling or knowledge representation technique for structured data repository premised on collection of concepts with their semantic relationships and constraints on particular area of knowledge. Example is wordNet which is linguistic based and popular ontology which has been greatly used to be part of ontology based information retrieval system development. However, the existing wordNet would affect the expected accurate results of such system owing to its overlapping return of senses. Therefore, this research aimed to design algorithm with the aid of extended Levenshtein similarity matching function and WordWeb to proffer solution to the militating problem. At the end, an enhanced wordNet that devoid of overlapping returns of senses for efficient polysemy representation in terms of user's time and system's memory would be achieved.
Parts of Speech tagging (POS) is an essential preliminary task of Natural Languages Processing (NLP). Its aim is to assign parts of speech tag to each word in corpus. The basic POS tags are noun, pronoun, verb, adjective and adverb, etc. POS tags are needed for speech analysis and recognition, Machine translation, Lexical analysis like word sense disambiguation, named entity recognitions, Information retrieval and this system also helped to uncover the sentiments of given text in opinion mining. At the same time, many Indian languages lack POS taggers because the research towards building basic resources like corpora and morphological analyzers is still in its infancy. Henceforth in this paper, a POS tagger for Telugu language, a South Indian language is proposed. In this model, the lexemes are tagged with various POS tags by using pre-tagged corpus, however a word may be tagged with multiple tags. This ambiguity in tag assignment is resolved with Stochastic Machine Learning Technique, i.e. Hidden Markov Model (HMM) Bigram tagger, which uses probabilistic information built based on contextual information or word tag sequences to resolve the ambiguity. In this system, the authors have developed a pre-tagged corpus of size 11000 words with standard communal tag sets for Telugu language and the same is used for testing and training the model. This model tested with input text data consists of different number of POS tags at word level and achieved the average performance accuracy of 91.27% in resolving the ambiguity.
Providing security and privacy for the cloud data is one of the most difficult tasks in recent days. The privacy of the sensitive information ought to be protecting from the unauthorized access for enhancing its security. Security is provided using traditional encryption and decryption process. One of the drawbacks of the traditional algorithm is that it has increased computational complexity, time consumption, and reduced security. The authors have proposed a scheme where the original data gets encrypted into two different values. Elliptical Curve Cryptography (ECC) and Homomorphic are combined to provide encryption. The data in each slice can be encrypted by using different cryptographic algorithms and encryption key before storing them in the cloud. The objective of this technique is to store data in a proper secure and safe manner in order to avoid intrusions and data attacks meanwhile it will reduce the cost and time to store the encrypted data in the Cloud Storage.
Data Mining is the process of extracting useful information from a large set of data. Market Basket Analysis is a technique of data mining which discovers an association between items with another. Market Basket Analysis refers to a process or technique, which identifies a customer's buying behavior or purchasing pattern, i.e. the items which are bought together by a customer in a single shopping cart. Market Basket Analysis is also termed as Association rule learning and another name for this technique is affinity Analysis. The main purpose of Market Basket Analysis is to extract the purchasing pattern of customers so that it increases the business efficiency and assists the retailers in making the decision regarding business in a profitable direction, increasing sales and make marketing strategies to compete with competitors. The main challenge for leading supermarkets is to attract a good number of customers, which can be done with the help of a data mining technique that is association rule mining. The frequent item sets are mined from the market basket to generate and after generation of the frequent items, the strongly associated item sets are generated with the help of support and confidence. This paper presents a recent survey of a supermarket for generating association rules to examine the customers’ buying or purchasing behavior.
